research-article

A Competitive Attentional Approach to Mitigating Model Drift in Adaptive Visual Tracking

Authors:

Sebastien Wong,

Anthony Milton,

Victor StamatescuAuthors Info & Claims

IVCNZ '14: Proceedings of the 29th International Conference on Image and Vision Computing New Zealand

Pages 1 - 6

https://doi.org/10.1145/2683405.2683406

Published: 19 November 2014 Publication History

Abstract

A critical issue for adaptive visual tracking is that of model drift, which occurs when the state space of the object of interest is polluted by observations that should have been attributed to background clutter. One approach to mitigating model drift in adaptive feature-learning visual tracking systems is to introduce prior information about the object of interest, such as key-frames. We propose an alternative solution to mitigating model drift, which is to track everything including sources of clutter and then assign observations to the tracks that best describe the observations. We demonstrate that by having multiple single target trackers (Shape Estimating Filters) that interact in a competitive attentional framework, observations from clutter (objects that are not of interest) can be explained-away allowing each tracker to focus its attention on its object of interest.

References

[1]

Bhattacharyya, A. On a Measure of Divergence between Two Statistical Populations Defined by their Probability Distributions. Bulletin of the Calcutta Mathematical Society 35 (1943), 99--109.

[2]

Cehovin, L., Kristan, M., and Leonardis, A. Robust visual tracking using an adaptive coupled-layer visual model. IEEE Trans. Pattern Anal. and Mach. Intell. 35, 4 (2013), 941--953.

Digital Library

[3]

Cho, J., and Yun, B. Selective-Attention Correlation Measure for Precision Video Tracking. IEICE - Trans. Inf. Syst. E88-D, 5 (2005), 1041--1049.

Digital Library

[4]

Collins, R. T., Yanxi, L., and Leordeanu, M. Online Selection of Discriminative Tracking Features. IEEE Trans. Pattern Anal. Mach. Intell 27, 10 (2005), 1631--1643.

Digital Library

[5]

Comaniciu, D., Ramesh, V., and Meer, P. Kernel-based Object Tracking. IEEE Trans. Pattern Anal. and Mach. Intell. 25, 5 (2003), 564--577.

Digital Library

[6]

D'Orazio, T., Leo, M., Mosca, N., Spagnolo, P., and Mazzeo, P. A Semi-Automatic System for Ground Truth Generation of Soccer Video Sequences. In IEEE Advanced Video and Signal Based Surveillance (2009), IEEE, pp. 559--564.

Digital Library

[7]

Grabner, H., Leistner, C., and Bischof, H. Semi-Supervised On-Line Boosting for Robust Tracking. Computer Vision - ECCV 2008 (2008), 234--247.

Digital Library

[8]

Grossberg, S. Adaptive pattern classification and universal recoding: I. Parallel development and coding of neural feature detectors. Biological cybernetics 23, 3 (1976), 121--134.

Digital Library

[9]

Hou, X., and Zhang, L. Saliency Detection: A Spectral Residual Approach. In Computer Vision - CVPR 2007 (2007), IEEE, pp. 1--8.

[10]

Kalal, Z., Mikolajczyk, K., and Matas, J. Tracking-learning-detection. IEEE Trans. Pattern Anal. and Mach. Intell. 34, 7 (2012), 1409--1422.

Digital Library

[11]

Kristan, M., et al. The Visual Object Tracking VOT2013 challenge results. In IEEE Workshop on Video Object Tracking (in conjunction with ICCV) (2013), IEEE, pp. 98--111.

Digital Library

[12]

Lu, H., Lu, S., and Chen, Y. Robust Tracking Based on Pixel-Wise Spatial Pyramid and Biased Fusion. Computer Vision--ACCV 2010 (2011), 165--176.

Digital Library

[13]

Lu, H., Zhang, W., and Chen, Y. On Feature Combination and Multiple Kernel Learning for Object Tracking. Computer Vision--ACCV 2010 (2011), 511--522.

Digital Library

[14]

Mahadevan, V., and Vasconcelos, N. Biologically inspired object tracking using center-surround saliency mechanisms. IEEE Trans. Pattern Anal. Mach. Intell 35, 3 (2013), 541--554.

Digital Library

[15]

Matthews, L., Ishikawa, T., and Baker, S. The Template Update Problem. IEEE Trans. Pattern Anal. Mach. Intell 26, 6 (2004), 810--815.

Digital Library

[16]

Rubner, Y., Tomasi, C., and Guibas, L. J. A Metric for Distributions with Applications to Image Databases. In Computer Vision - ICCV 1998 (1998), pp. 59--66.

Digital Library

[17]

Strens, M., and Gregory, I. Tracking in Cluttered Images. Image and Vision Computing 21, 10 (2003), 891--911.

[18]

Wilson, F., Scalaidhe, S., and Goldman-Rakic, P. Dissociation of Object and Spatial Processing Domains in Primate Prefrontal Cortex. Science 260, 5116 (1993), 1955--1958.

[19]

Wong, S. Advanced Correlation Tracking of Objects in Cluttered Imagery. In SPIE Acquisition, Tracking, and Pointing XIX (2005), vol. 5810, SPIE, pp. 158--169.

[20]

Wong, S., and Kearney, D. Relating Image, Shape, Position and Velocity in Visual Tracking. In SPIE Acquisition, Tracking, Pointing, and Laser Systems Technologies XXIII (2009), vol. 7338, SPIE.

[21]

Yin, Z., and Collins, R. Moving Object Localization in Thermal Imagery by Forward-backward MHI. In Computer Vision and Pattern Recognition Workshop, 2006 (2006), pp. 133--133.

Digital Library

[22]

Yin, Z., Porikli, F., and Collins, R. Likelihood Map Fusion for Visual Object Tracking. In Computer Vision - WACV 2008 (2008), pp. 1--7.

Digital Library

Cited By

Wu JSu XYuan QShen HZhang L(2022)Multivehicle Object Tracking in Satellite Video Enhanced by Slow Features and Motion FeaturesIEEE Transactions on Geoscience and Remote Sensing10.1109/TGRS.2021.313912160(1-26)Online publication date: 2022
https://doi.org/10.1109/TGRS.2021.3139121
Wong SStamatescu VGatt AKearney DLee IMcDonnell M(2017)Track Everything: Limiting Prior Knowledge in Online Multi-Object RecognitionIEEE Transactions on Image Processing10.1109/TIP.2017.269674426:10(4669-4683)Online publication date: Oct-2017
https://doi.org/10.1109/TIP.2017.2696744

Index Terms

A Competitive Attentional Approach to Mitigating Model Drift in Adaptive Visual Tracking
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision problems
      2. Computer vision tasks
        Scene understanding

Recommendations

Reducing drift in differential tracking

We present methods for turning pair-wise registration algorithms into drift-free trackers. Such registration algorithms are abundant, but the simplest techniques for building trackers on top of them exhibit either limited tracking range or drift. Our ...
Lens model selection for visual tracking
PR'05: Proceedings of the 27th DAGM conference on Pattern Recognition

A standard approach to generate a camera pose from images of a single moving camera is Structure From Motion (SfM). When aiming on a practical implementation of SfM often a camera is needed that is lightweight and small. This work analyses which is the ...
Context-aware and attentional visual object tracking

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Other conferences

IVCNZ '14: Proceedings of the 29th International Conference on Image and Vision Computing New Zealand

November 2014

298 pages

ISBN:9781450331845

DOI:10.1145/2683405

Co-chairs:
John Perrone,
Michael Mayo,
Anthony Blake,
General Chair:
Michael J. Cree,
Publications Chair:
Lee Streeter

Copyright © 2014 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

In-Cooperation

The University of Waikato

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 19 November 2014

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Qualifiers

Research-article
Research
Refereed limited

Conference

IVCNZ '14

IVCNZ '14: The 29th International Conference on Image and Vision Computing New Zealand

November 19 - 21, 2014

Hamilton, New Zealand

Acceptance Rates

IVCNZ '14 Paper Acceptance Rate 55 of 74 submissions, 74%;

Overall Acceptance Rate 55 of 74 submissions, 74%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

2
Total Citations
View Citations
127
Total Downloads

Downloads (Last 12 months)3
Downloads (Last 6 weeks)0

Reflects downloads up to 10 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Wu JSu XYuan QShen HZhang L(2022)Multivehicle Object Tracking in Satellite Video Enhanced by Slow Features and Motion FeaturesIEEE Transactions on Geoscience and Remote Sensing10.1109/TGRS.2021.313912160(1-26)Online publication date: 2022
https://doi.org/10.1109/TGRS.2021.3139121
Wong SStamatescu VGatt AKearney DLee IMcDonnell M(2017)Track Everything: Limiting Prior Knowledge in Online Multi-Object RecognitionIEEE Transactions on Image Processing10.1109/TIP.2017.269674426:10(4669-4683)Online publication date: Oct-2017
https://doi.org/10.1109/TIP.2017.2696744

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents